The signature of a person is one of the most popular and legally accepted behavioral biometrics that provides a secure means for verification and personal identification in many applications such as financial, commercial and legal transactions. The objective of the signature verification system is to classify between genuine and forged signatures that are often associated with intrapersonal and interpersonal variability. Unlike other languages, Arabic has unique features; it contains diacritics, ligatures, and overlapping. Because of lacking any form of dynamic information during the Arabic signature’s writing process, it will be more difficult to obtain higher verification accuracy. This paper addresses the above difficulty by introducing a novel offline Arabic signature verification algorithm. The key point is using multiple feature fusion with fuzzy modeling to capture different aspects of a signature individually in order to improve the verification accuracy. State-of-the-art techniques adopt the fuzzy set to describe the properties of the extracted features to handle a signature’s uncertainty; this work also employs the fuzzy variables to describe the degree of similarity of the signature’s features to deal with the ambiguity of questioned document examiner judgment of signature similarity. It is concluded from the experimental results that the verification system performs well and has the ability to reduce both False Acceptance Rate (FAR) and False Rejection Rate (FRR).